Haodong Niu, Yunbo Shi, Kuo Zhao, Jinzhou Liu, Xiaohui Yang, Canda Zheng
To address the limitations of conventional discrete ammonia-monitoring schemes, this study proposes a closed-loop sensing-inference architecture that integrates a distributed chemical-sensing network with a physics-informed neural network (PINN) to achieve high-fidelity three-dimensional dynamic reconstruction of gas diffusion in confined environments. A distributed sensor array based on a PPy/Graphene/WO3 ternary nanocomposite provides real-time wireless monitoring and reliable observational data streams owing to its sub-ppm detection limit and high signal-to-noise ratio. Fick's second law of diffusion and Neumann no-flux boundary conditions are embedded in a mesh-free PINN, and rolling horizon data assimilation (RHDA) is introduced to dynamically fine-tune the network weights with high-frequency real-time observations, thereby establishing a real-time closed-loop correction between theoretical inference and the monitored environment. The proposed method achieves accurate three-dimensional concentration-field reconstruction under steady-state conditions, markedly suppresses errors and maintains robustness under unknown abrupt concentration disturbances, and mitigates the temporal divergence of conventional data-driven models during long-term purely physical extrapolation without data support. Thus, the framework combines hardware sensitivity, computational efficiency, and macroscopic physical generalization.